Article
Mathematics
Xin-Yu Tian, Xincheng Shi, Cheng Peng, Xiao-Jian Yi
Summary: The paper introduces a nonhomogeneous Poisson process model based on the AMSAA model, considering covariate effects. Parameter estimation of the model is done using maximum likelihood, and the statistical properties of the estimation are comprehensively derived through martingale theory. Further inferences like confidence interval estimation and hypothesis tests are designed for the model, and the performance and properties of the method are verified in a simulation study.
Article
Mathematics
Chanseok Park
Summary: This paper considers parameter estimation of the Weibull distribution with interval-censored data using the expectation-maximization (EM) algorithm. The results show that the estimates obtained using the EM method have superior convergence properties compared to conventional Newton-type methods. Finally, a numerical study is provided to illustrate the advantages of the proposed method.
Article
Mathematical & Computational Biology
Kelly Van Lancker, Oliver Dukes, Stijn Vansteelandt
Summary: The analysis of randomized trials with time-to-event endpoints is often affected by censoring, leading to concerns about model misspecification and treatment effect estimand. A proposed variable selection strategy aims to address these concerns and produce a valid test of the null hypothesis in large samples.
STATISTICS IN MEDICINE
(2021)
Article
Biochemical Research Methods
Qian Gao, Yu Zhang, Hongwei Sun, Tong Wang
Summary: This paper reviews the methods for estimating causal effects in observational studies and evaluates their performance in high-dimensional settings. The simulation experiments show that GLiDeR and hdCBPS approaches perform well in terms of estimation accuracy, but further studies are needed for constructing valid confidence intervals.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Mathematical & Computational Biology
Paul N. Zivich, Michael G. Hudgens, Maurice A. Brookhart, James Moody, David J. Weber, Allison E. Aiello
Summary: This paper discusses the common occurrence of interference in medicine and public health, and extends the TMLE method to handle interference through the network-TMLE approach. Simulation studies demonstrate that network-TMLE performs well in scenarios with interference, but issues arise when policies are not well-supported by observed data, leading to potentially poor confidence interval coverage.
STATISTICS IN MEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
Tao Zhang, Hao-Ran Shan, Max A. Little
Summary: This paper introduces a graph neural network model called Causal GraphSAGE (C-GraphSAGE) that incorporates causal inference into the sampling stage of GraphSAGE to improve classifier robustness. Experimental results demonstrate that C-GraphSAGE outperforms other graph neural network models in terms of classification performance when perturbation is present.
PATTERN RECOGNITION
(2022)
Article
Engineering, Civil
Abhishek Goyal, Alessia Flammini, Renato Morbidelli, Corrado Corradini, Rao S. Govindaraju
Summary: The impact of observations on the maximum likelihood estimates (MLE) of the Ks distribution parameters is evaluated in this study. Based on data from rainfall-runoff events, the results demonstrate the role of temporal variation of rainfall in resolving the Ks field for a rainfall event.
JOURNAL OF HYDROLOGY
(2023)
Article
Statistics & Probability
Koen Jochmans
Summary: This article investigates inference in linear regression models that are robust to heteroscedasticity and the presence of many control variables. The usual heteroscedasticity-robust estimators of the covariance matrix are inconsistent when the number of control variables increases at the same rate as the sample size. An alternative covariance-matrix estimator for such a setting is proposed, and high-level conditions for size-correct inference as well as more primitive conditions for three special cases are provided.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2022)
Article
Biochemical Research Methods
Sarah Lutteropp, Celine Scornavacca, Alexey M. Kozlov, Benoit Morel, Alexandros Stamatakis
Summary: NetRAX is a tool for maximum likelihood inference of phylogenetic networks in the absence of incomplete lineage sorting. It efficiently computes the phylogenetic likelihood function on trees and extends them to phylogenetic networks. The tool can infer ML phylogenetic networks from partitioned multiple sequence alignments and provides the results in Extended Newick format.
Article
Neurosciences
Thomas Maullin-Sapey, Thomas E. Nichols
Summary: Large-scale, shared datasets in neuroimaging pose challenges to existing tools in terms of scale and complexity. To address these challenges, researchers have developed the BLMM toolbox, an efficient tool for large-scale fMRI linear mixed models analysis.
Article
Biology
Shuwei Li, Limin Peng
Summary: This article fills the research gap by proposing a nonparametric maximum likelihood estimator for causal treatment effects in time-to-event outcomes subject to interval censoring. A reliable and computationally stable expectation-maximization algorithm is designed, and the asymptotic properties of the proposed estimators are established. Extensive simulation studies and an application to colorectal cancer screening data demonstrate the satisfactory performance and advantages of the proposed method over naive methods.
Article
Environmental Sciences
Heather K. Amato, Caitlin Hemlock, Kristin L. Andrejko, Anna R. Smith, Nima S. Hejazi, Alan E. Hubbard, Sharat C. Verma, Ramesh K. Adhikari, Dhiraj Pokhrel, Kirk Smith, Jay P. Graham, Amod Pokhrel
Summary: This study estimated the effect of daily reported biogas cookstove use on incident diarrhea among children under 5 years old in the Kavrepalanchok District of Nepal. The results showed that the use of biogas cookstoves was associated with an increased risk of diarrhea, especially among breastfed children and during the dry season.
ENVIRONMENTAL HEALTH PERSPECTIVES
(2022)
Article
Statistics & Probability
Yu Luo, Daniel J. Graham, Emma J. McCoy
Summary: Frequentist semiparametric theory has been widely used in the development of doubly robust causal estimation. In this paper, a fully semiparametric Bayesian framework is proposed for DR causal inference. The framework combines nonparametric Bayesian procedures with empirical likelihood via semiparametric linear regression, allowing for consistent parameter estimation even with correct specification of only one model.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE
(2023)
Article
Biochemistry & Molecular Biology
Ambrosio Torres, Pablo A. Goloboff, Santiago A. Catalano
Summary: The study compared the results of three concatenated phylogenetic methods in 157 empirical datasets and found that the resulting trees were largely similar, with differences mostly in nodes of lower support. Most studies reached similar conclusions for the three methods, with discordance involving nodes considered challenging in systematics. The differences between methods were more prominent in datasets analyzing relationships at higher taxonomic levels, independent of the number of characters included in the datasets.
MOLECULAR PHYLOGENETICS AND EVOLUTION
(2021)
Article
Mathematics
Abdullah Fathi, Al-Wageh A. Farghal, Ahmed A. Soliman
Summary: This article discusses the estimation of parameters and the analysis of reliability in the Weibull inverted exponential (WIE) distribution based on progressive first-failure censoring (PFFC) data. Maximum likelihood (ML) estimators are obtained for non-Bayesian inference and their existence is verified. Confidence intervals (CIs) for the parameters and the reliability are constructed using the asymptotic normality of ML estimators and the delta method. Bayesian inference is performed using Lindley's approximation and Markov chain Monte Carlo (MCMC) techniques to obtain Bayes estimators and corresponding credible intervals (CRIs). The efficiency of the developed methods is evaluated through numerous Monte Carlo simulations, and a numerical example is analyzed for illustration purposes.